论文部分内容阅读
针对斜轴式柱塞泵零部件故障信息被泵本身的流体冲击、机械振动所淹没的问题 ,采用小波包将振动信号分解到不同的频带以提取有关部件的故障信息 ,并将小波包分解在不同频带反映斜轴泵工作状况的振动特征信息作为故障样本 ,研究人工神经网络结合小波分析对斜轴泵进行故障诊断的方法 ,建立了相应的 BP神经网络。研究结果表明训练成功的 BP网络可作为智能分类器对斜轴泵的常见故障进行识别和诊断。
Aiming at the problem that the failure information of the tilting axis plunger pump is affected by the fluid impact of the pump itself and the mechanical vibration, the wavelet packet is used to decompose the vibration signal into different frequency bands to extract the fault information of the relevant components and to decompose the wavelet packet in In different frequency bands, the vibration characteristic information of inclinometer pump working condition is taken as the fault sample. The artificial neural network and wavelet analysis are used to diagnose the incline pump fault, and the corresponding BP neural network is established. The results show that the trained BP neural network can be used as an intelligent classifier to identify and diagnose common faults of inclined axis pumps.